Tracking people in RGBD videos using deep learning and motion clues

详细信息    查看全文

• 作者：Hongyang Xue ^{hyxue@outlook.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yao Liu ^{xuanyao0111@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Deng Cai ; ^{dengcai@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xiaofei He ^{xiaofei_h@qq.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：RGB-D ; Human tracking ; Pedestrian trajectory ; Convolutional neural network ; Deep learning
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：5 September 2016
• 年：2016
• 卷：204
• 期：Complete
• 页码：70-76
• 全文大小：2599 K

文摘

Tracking people in videos is an important topic in surveillance. We consider the problem of human tracking in RGBD videos filmed by sensors such as MS Kinect and Primesense. Our goal is to track persons where the crowd of people is known in advance or all persons in the video have appeared in the very beginning. Thus we can train a classifier to help classify and track persons across the video. A deep learning model trained with big data has been proved to be an effective classifier for various kinds of objects. We propose to train a deep convolutional neural network, which improves tracking performance, to classify people. And a motion model based on spatial and kinetic clues is combined with the network to track people in the scene. We demonstrate the effectiveness of our method by evaluating it on several datasets and comparing with traditional methods like SVM.